Removal of high density salt and pepper noise using BPANN-modified median filter technique

In this paper an efficient yet simple approach of salt and pepper noise removal based on back propagation neural network and adaptive median filtering has been suggested. The proposed method uses supervised learning capability of back-propagation neural network to remove the salt and pepper noise in first phase and adaptive median filter is used to enhance the image quality in second phase. It overcomes all drawbacks of conventional median filtering by preserving the fine details. Experimental results show that the algorithm performs better than neural network based model & other conventional filtering mechanisms. Performance is exceptionally good even for high density noised images.